Roboflow

Drones + CV are solving problems you wouldn’t expect. Being able to remotely monitor agriculture and infrastructure means the world is running more seamlessly for everyone. #AI #ComputerVision

Our most in-depth interview on the state of vision AI and what it will take to make sure visual data is a core input for software in the future

Computer vision is helping the world’s largest logistics businesses operate more smoothly. Being able to use video and image data as an input will change every industry. #AI #ComputerVision

I've started a series of short experiments using advanced Vision-Language Models (#VLM) to improve #robot #perception. In the first article, I showed how simple prompt engineering can steer Grounded SAM 2 to produce impressive detection and segmentation results. However, the major challenge remains: most #robotic systems, including mine, lack GPUs powerful enough to run these large models in real time. In my latest experiment, I tackled this issue by using Grounded SAM 2 to auto-label a dataset and then fine-tuning a compact #YOLO v8 model. The result? A small, efficient model that detects and segments my SHL-1 robot in real time on its onboard #NVIDIA #Jetson computer! If you're working in #robotics or #computervision and want to skip the tedious process of manually labeling datasets, check out my article (code included). I explain how I fine-tuned a YOLO model in just a couple of hours instead of days. Thanks to Roboflow and its amazing #opensource tools for making all of this more straightforward. #AI #MachineLearning #DeepLearning

Humans navigate the world with our sense of sight, this should also be true for software and computers. Thanks to everyone building in the vision space, we are making this a reality. #AI #ComputerVision

Running into GPU access or cost problems? Our newest feature lets you run models like SAM 2, PaliGemma, and Florence-2 instantly on private dedicated GPUs. It just takes a few clicks to get a dev or production environment set up and you can start building immediately. Reasons we are seeing people use Dedicated Deployments: Dedicated Resources: Get cloud servers allocated specifically for your use, ensuring consistent performance for your models. Model Library: Immediate access to foundation models, vision-language models, OCR models, object detection, and more. Easy Integration: Each deployment receives a subdomain within roboflow.cloud, simplifying integration with your applications. Available in all accounts, try it out today or read more here: https://buff.ly/41vjdjG #AI #ComputerVision

We're going live at 11am ET to unpack the latest in Computer Vision research. Join Roboflow ML Engineers Isaac Robinson and Peter Robicheaux as they share their NeurIPS talk: "Best of Vision 2024: Research Recap". This session is open to all; please note it will be one of our more technical webinars given the theme. RSVP link in the comments

YOLOv5 vs. YOLO11: Comparing Detection Quality 🔴 🟢 🔵 I'm working on a new annotator for supervision-0.26.0 that lets you compare predictions from two detection models. While working on example visualizations, I noticed that YOLO11 struggles to detect objects further from the camera. Is this a known limitation or something specific to my data? Here's how I'm visualizing the comparisons: 🔴 - detected only by YOLOv5m 🟢 - detected only by YOLO11m 🔵 - detected by both models ⮑ 🔗 use supervision for benchmarking: https://lnkd.in/d57M3c32 And, of course, you can compare any pair of detectors. More comparisons below 👇🏻 #computervision #objectdetection

In this final part of the conveyor belt counter series we deploy the computer vision model. Here’s how to do it: > Choose deployment method: We select localhost so we can run inference on video stream locally. > Set up your environment: Make sure to have Python and Docker configured on your computer and pull the inference server. > Deploy your workflow using Python on your computer. What projects should we tackle next? Try deploy your own workflows and share your experience in the comments! #AI #ComputerVision #SmartManufacturing

Building complex vision AI applications is time consuming. Using Workflows can speed things up. Here's how: > Create a new Workflow > Add an object detection block > Use the ByteTrack block to prevent double counting > Define a line to detect objects crossing a specific area > Add visualization blocks to see your model in action What application should we build next? Try it out and share your thoughts in the comments! Check out the links below for guides and other applications built with Workflows. #AI #AutomationTools #SmartManufacturing